Non-invasive ML methods for diagnosis of congenital heart disease associated with pulmonary arterial hypertension
ObjectiveCongenital heart disease with pulmonary arterial hypertension (CHD-PAH), caused by CHD, is associated with high clinical mortality. Hence, timely diagnosis is imperative for treatment.ApproachTwo non-invasive diagnosis algorithms of CHD-PAH were put forward in this review, which were direct...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2024.1502725/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841561067418812416 |
|---|---|
| author | Yuyang Gao Pengyue Ma Jiahua Pan Hongbo Yang Tao Guo Weilian Wang |
| author_facet | Yuyang Gao Pengyue Ma Jiahua Pan Hongbo Yang Tao Guo Weilian Wang |
| author_sort | Yuyang Gao |
| collection | DOAJ |
| description | ObjectiveCongenital heart disease with pulmonary arterial hypertension (CHD-PAH), caused by CHD, is associated with high clinical mortality. Hence, timely diagnosis is imperative for treatment.ApproachTwo non-invasive diagnosis algorithms of CHD-PAH were put forward in this review, which were direct three-divided and two-stage classification models. Pre-processing in both algorithms focuses on segmentation of heart sounds into discrete cardiac cycles. Both the dual-threshold and Bi-LSTM (Bi-directional Long Short-Term Memory) methods demonstrate efficacy. In the feature extraction phase, the direct three-divided model integrate time-, frequency-, and energy-domain features with deep learning features. While the two-stage classification model sequentially extracts sub-band envelopes and short-time energy of cardiac cycle. In the classification phase, considering the lack of CHD-PAH data, ensemble learning was widely used.Main resultsAn accuracy of 88.61% was achieved with direct three-divided model and 90.9% with two-stage classification model.SignificanceBy analyzing and discussing these algorithms, future research directions of CHD-PAH assisted diagnosis were discussed. It is hoped that it will provide insight into prediction of CHD-PAH. Thus saving people from death due to untimely assistance. |
| format | Article |
| id | doaj-art-cea1a758a5314adbb7afc835f9a6a110 |
| institution | Kabale University |
| issn | 1664-042X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj-art-cea1a758a5314adbb7afc835f9a6a1102025-01-03T06:47:26ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2025-01-011510.3389/fphys.2024.15027251502725Non-invasive ML methods for diagnosis of congenital heart disease associated with pulmonary arterial hypertensionYuyang Gao0Pengyue Ma1Jiahua Pan2Hongbo Yang3Tao Guo4Weilian Wang5Country School of Information Science and Engineering, Yunnan University, Kunming, ChinaCountry School of Information Science and Engineering, Yunnan University, Kunming, ChinaFuwai Yunnan Hospital, Chinese Academy of Medical Sciences, Affiliated Cardiovascular Hospital of Kunming Medical University, Kunming, ChinaFuwai Yunnan Hospital, Chinese Academy of Medical Sciences, Affiliated Cardiovascular Hospital of Kunming Medical University, Kunming, ChinaFuwai Yunnan Hospital, Chinese Academy of Medical Sciences, Affiliated Cardiovascular Hospital of Kunming Medical University, Kunming, ChinaCountry School of Information Science and Engineering, Yunnan University, Kunming, ChinaObjectiveCongenital heart disease with pulmonary arterial hypertension (CHD-PAH), caused by CHD, is associated with high clinical mortality. Hence, timely diagnosis is imperative for treatment.ApproachTwo non-invasive diagnosis algorithms of CHD-PAH were put forward in this review, which were direct three-divided and two-stage classification models. Pre-processing in both algorithms focuses on segmentation of heart sounds into discrete cardiac cycles. Both the dual-threshold and Bi-LSTM (Bi-directional Long Short-Term Memory) methods demonstrate efficacy. In the feature extraction phase, the direct three-divided model integrate time-, frequency-, and energy-domain features with deep learning features. While the two-stage classification model sequentially extracts sub-band envelopes and short-time energy of cardiac cycle. In the classification phase, considering the lack of CHD-PAH data, ensemble learning was widely used.Main resultsAn accuracy of 88.61% was achieved with direct three-divided model and 90.9% with two-stage classification model.SignificanceBy analyzing and discussing these algorithms, future research directions of CHD-PAH assisted diagnosis were discussed. It is hoped that it will provide insight into prediction of CHD-PAH. Thus saving people from death due to untimely assistance.https://www.frontiersin.org/articles/10.3389/fphys.2024.1502725/fullcongenital heart disease associated with pulmonary arterial hypertensionmachine learningsegmentationheart sounds classificationensemble learning |
| spellingShingle | Yuyang Gao Pengyue Ma Jiahua Pan Hongbo Yang Tao Guo Weilian Wang Non-invasive ML methods for diagnosis of congenital heart disease associated with pulmonary arterial hypertension Frontiers in Physiology congenital heart disease associated with pulmonary arterial hypertension machine learning segmentation heart sounds classification ensemble learning |
| title | Non-invasive ML methods for diagnosis of congenital heart disease associated with pulmonary arterial hypertension |
| title_full | Non-invasive ML methods for diagnosis of congenital heart disease associated with pulmonary arterial hypertension |
| title_fullStr | Non-invasive ML methods for diagnosis of congenital heart disease associated with pulmonary arterial hypertension |
| title_full_unstemmed | Non-invasive ML methods for diagnosis of congenital heart disease associated with pulmonary arterial hypertension |
| title_short | Non-invasive ML methods for diagnosis of congenital heart disease associated with pulmonary arterial hypertension |
| title_sort | non invasive ml methods for diagnosis of congenital heart disease associated with pulmonary arterial hypertension |
| topic | congenital heart disease associated with pulmonary arterial hypertension machine learning segmentation heart sounds classification ensemble learning |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2024.1502725/full |
| work_keys_str_mv | AT yuyanggao noninvasivemlmethodsfordiagnosisofcongenitalheartdiseaseassociatedwithpulmonaryarterialhypertension AT pengyuema noninvasivemlmethodsfordiagnosisofcongenitalheartdiseaseassociatedwithpulmonaryarterialhypertension AT jiahuapan noninvasivemlmethodsfordiagnosisofcongenitalheartdiseaseassociatedwithpulmonaryarterialhypertension AT hongboyang noninvasivemlmethodsfordiagnosisofcongenitalheartdiseaseassociatedwithpulmonaryarterialhypertension AT taoguo noninvasivemlmethodsfordiagnosisofcongenitalheartdiseaseassociatedwithpulmonaryarterialhypertension AT weilianwang noninvasivemlmethodsfordiagnosisofcongenitalheartdiseaseassociatedwithpulmonaryarterialhypertension |